add module for mash dist (#1193)

* add module for mash dist

* fix lint

Co-authored-by: Gregor Sturm <mail@gregor-sturm.de>

modules/mash/dist/main.nf

@@ -0,0 +1,34 @@
+process MASH_DIST {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::mash=2.3" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mash:2.3--he348c14_1' :
+        'quay.io/biocontainers/mash:2.3--he348c14_1' }"
+
+    input:
+    tuple val(meta), path(query)
+    path reference
+
+    output:
+    tuple val(meta), path("*.txt"), emit: dist
+    path "versions.yml"           , emit: versions
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    mash \\
+        dist \\
+        -p $task.cpus \\
+        $args \\
+        $reference \\
+        $query > ${prefix}.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        mash: \$(mash --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/mash/dist/meta.yml

@@ -0,0 +1,45 @@
+name: mash_dist
+description: Calculate Mash distances between reference and query seqeunces
+keywords:
+  - mash/dist
+tools:
+  - mash:
+      description: Fast sequence distance estimator that uses MinHash
+      homepage: https://github.com/marbl/Mash
+      documentation: https://mash.readthedocs.io/en/latest/sketches.html
+      tool_dev_url: https://github.com/marbl/Mash
+      doi: "10.1186/s13059-016-0997-x"
+      licence: ['https://github.com/marbl/Mash/blob/master/LICENSE.txt']
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reference:
+      type: file
+      description: FASTA, FASTQ or Mash sketch
+      pattern: "*.{fasta,fasta.gz,fastq,fastq.gz,msh}"
+  - query:
+      type: file
+      description: FASTA, FASTQ or Mash sketch
+      pattern: "*.{fasta,fasta.gz,fastq,fastq.gz,msh}"
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - dist:
+      type: file
+      description: The results from mash dist
+      pattern: "*.txt"
+
+authors:
+  - "@rpetit3"

tests/config/pytest_modules.yml

@@ -900,6 +900,10 @@ mapdamage2:
   - modules/mapdamage2/**
   - tests/modules/mapdamage2/**
 
+mash/dist:
+  - modules/mash/dist/**
+  - tests/modules/mash/dist/**
+
 mash/sketch:
   - modules/mash/sketch/**
   - tests/modules/mash/sketch/**

tests/modules/mash/dist/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { MASH_DIST } from '../../../../modules/mash/dist/main.nf'
+
+workflow test_mash_dist {
+    
+    input = [ 
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true)
+    ]
+
+    reference =  file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
+    MASH_DIST ( input, reference )
+}

tests/modules/mash/dist/nextflow.config

@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}

tests/modules/mash/dist/test.yml

@@ -0,0 +1,10 @@
+- name: mash dist test_mash_dist
+  command: nextflow run tests/modules/mash/dist -entry test_mash_dist -c tests/config/nextflow.config
+  tags:
+    - mash
+    - mash/dist
+  files:
+    - path: output/mash/test.txt
+      md5sum: 1dfd5b53e1996f9fdb9d260b3e81c4d6
+    - path: output/mash/versions.yml
+      md5sum: f786d48a9af59e823d19c171969d0d50